Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description discloses important side effects and hidden behaviors: invoke performs a one-off install behind the scenes, auth-gated or unpaid tools return user-action links, and write operations require workspace owner/admin. These details go well beyond the generic annotations (readOnlyHint=false, destructiveHint=false) and align with them, adding genuine behavioral transparency.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is dense and lengthy, but the tool itself is a broad multi-action dispatcher with 23 parameters and 15 sub-actions, so nearly every sentence adds necessary guidance. The flow-oriented structure (search → describe → invoke, then install, then prompt library) helps navigation, though bullet points or section breaks would improve scannability.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description covers the core discovery-to-invocation loop, auth and wallet failure handling, permission requirements, one-off vs permanent install semantics, and the entire prompt-library subdomain. It does not explain return shapes, error/retry behavior, or some secondary parameters, and there is no output schema to compensate, but given the tool's complexity this is still a reasonably complete overview.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With schema description coverage at 0%, the description compensates by explaining the key dispatcher parameters: action values, mcp_id usage in search/describe, tool_id selection for invoke, arguments for the invoke call, and prompt_slug/prompt_vars for prompt-library actions. However, several parameters like limit, query, immediate, tier_slug, conversation, cancel_reason, and report_context remain undocumented, so the compensation is strong but not complete.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly identifies marketplace as the official in-platform catalog and execution path, with specific verbs for each sub-action: search, describe, invoke, install, list_tools, subscribe/cancel, report_bug, request_mcp, and the prompt-library actions. It also differentiates itself from sibling tools by positioning report_bug as one of its own sub-actions and framing the tool as the central MCP discovery and running mechanism.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives explicit when-to-use guidance, especially 'Use install only to make an MCP PERMANENT' and 'prefer invoke for a single/occasional use.' It also explains conditional flows for auth and payment failures ('returns a connect link', 'returns a checkout/top-up link ... then you retry') and states that writes require workspace owner/admin, providing clear decision rules for the agent.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.